black-forest-labs/flux-kontext-dev-lora 🔢📝❓🖼️✓ → 🖼️
About
FLUX.1 Kontext[dev] image editing model for running lora finetunes

Example Output
Prompt:
"render this image like a ps1 game (no UI)"
Output

Performance Metrics
4.40s
Prediction Time
4.40s
Total Time
All Input Parameters
{ "prompt": "render this image like a ps1 game (no UI)", "go_fast": true, "guidance": 2.5, "megapixels": "1", "input_image": "https://replicate.delivery/pbxt/NMRuqfZykP9mm4KdF8PL8r7Y73Ffk3BZyNjCfC0kVTJEtcRt/cool_selfie.webp", "aspect_ratio": "match_input_image", "lora_weights": "https://huggingface.co/fofr/flux-kontext-dev-ps1-lora/resolve/main/flux-kontext-dev-ps1-lora.safetensors", "lora_strength": 1, "output_format": "webp", "output_quality": 80, "num_inference_steps": 30 }
Input Parameters
- seed
- Random seed for reproducible generation. Leave blank for random.
- prompt (required)
- Text description of what you want to generate, or the instruction on how to edit the given image.
- guidance
- Guidance scale for generation
- megapixels
- Approximate number of megapixels for generated image
- input_image (required)
- Image to use as reference. Must be jpeg, png, gif, or webp.
- aspect_ratio
- Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.
- lora_weights
- Path to the lora weights
- lora_strength
- Strength of the lora
- output_format
- Output image format
- output_quality
- Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
- num_inference_steps
- Number of inference steps
- disable_safety_checker
- Disable NSFW safety checker
Output Schema
Output
Example Execution Logs
Lora already loaded Using seed: 59836 Target dimensions: NonexNone Total safe images: 1 out of 1
Version Details
- Version ID
50c10b8f14af90fda0a4bf3bbfdda263ddb0f2b3e32e4735dcc6ee7156d7ed6f
- Version Created
- July 22, 2025